ppo-Huggy / run_logs /timers.json
k0T0z's picture
Huggy
160ebee
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4009405374526978,
"min": 1.4009405374526978,
"max": 1.4300428628921509,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70491.125,
"min": 68710.8046875,
"max": 78672.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.19683655536028,
"min": 80.4413680781759,
"max": 387.6434108527132,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49046.0,
"min": 49016.0,
"max": 50353.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49518.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49518.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.392223834991455,
"min": 0.14783312380313873,
"max": 2.500406503677368,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1361.1754150390625,
"min": 18.922639846801758,
"max": 1439.838134765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.602500440051979,
"min": 1.8791981327813119,
"max": 3.9328686275836304,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2049.822750389576,
"min": 240.53736099600792,
"max": 2277.130935370922,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.602500440051979,
"min": 1.8791981327813119,
"max": 3.9328686275836304,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2049.822750389576,
"min": 240.53736099600792,
"max": 2277.130935370922,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016940641839108945,
"min": 0.012535270133392057,
"max": 0.019697158142662374,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05082192551732684,
"min": 0.02651422555015112,
"max": 0.05624104933328151,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0536278850502438,
"min": 0.02142168323819836,
"max": 0.06740946099162101,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1608836551507314,
"min": 0.04284336647639672,
"max": 0.19240630567073821,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4228988590666594e-06,
"min": 3.4228988590666594e-06,
"max": 0.000295347676550775,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0268696577199978e-05,
"min": 1.0268696577199978e-05,
"max": 0.0008437482187505997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114093333333335,
"min": 0.10114093333333335,
"max": 0.19844922500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30342280000000005,
"min": 0.20748989999999995,
"max": 0.5812494,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.69325733333332e-05,
"min": 6.69325733333332e-05,
"max": 0.0049226163275000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020079771999999963,
"min": 0.00020079771999999963,
"max": 0.014064345060000002,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1697083509",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697085869"
},
"total": 2360.072349774,
"count": 1,
"self": 0.4272630370001025,
"children": {
"run_training.setup": {
"total": 0.04603964799997584,
"count": 1,
"self": 0.04603964799997584
},
"TrainerController.start_learning": {
"total": 2359.599047089,
"count": 1,
"self": 4.482779744987511,
"children": {
"TrainerController._reset_env": {
"total": 7.238575672999957,
"count": 1,
"self": 7.238575672999957
},
"TrainerController.advance": {
"total": 2347.7674632980124,
"count": 232235,
"self": 4.685020966970569,
"children": {
"env_step": {
"total": 1864.71663018502,
"count": 232235,
"self": 1536.945246432026,
"children": {
"SubprocessEnvManager._take_step": {
"total": 324.93035506897843,
"count": 232235,
"self": 17.224164888054418,
"children": {
"TorchPolicy.evaluate": {
"total": 307.706190180924,
"count": 223064,
"self": 307.706190180924
}
}
},
"workers": {
"total": 2.8410286840156687,
"count": 232235,
"self": 0.0,
"children": {
"worker_root": {
"total": 2351.729741933046,
"count": 232235,
"is_parallel": true,
"self": 1106.3261171519985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009223879999922246,
"count": 1,
"is_parallel": true,
"self": 0.0003251240000281541,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005972639999640705,
"count": 2,
"is_parallel": true,
"self": 0.0005972639999640705
}
}
},
"UnityEnvironment.step": {
"total": 0.03199449999999615,
"count": 1,
"is_parallel": true,
"self": 0.00034216599993897034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023430500004906207,
"count": 1,
"is_parallel": true,
"self": 0.00023430500004906207
},
"communicator.exchange": {
"total": 0.030570994000015617,
"count": 1,
"is_parallel": true,
"self": 0.030570994000015617
},
"steps_from_proto": {
"total": 0.000847034999992502,
"count": 1,
"is_parallel": true,
"self": 0.0002473320000149215,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005997029999775805,
"count": 2,
"is_parallel": true,
"self": 0.0005997029999775805
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1245.4036247810477,
"count": 232234,
"is_parallel": true,
"self": 39.622216387158915,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.03421303103835,
"count": 232234,
"is_parallel": true,
"self": 84.03421303103835
},
"communicator.exchange": {
"total": 1031.4907129099295,
"count": 232234,
"is_parallel": true,
"self": 1031.4907129099295
},
"steps_from_proto": {
"total": 90.25648245292075,
"count": 232234,
"is_parallel": true,
"self": 33.88946898185077,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.36701347106998,
"count": 464468,
"is_parallel": true,
"self": 56.36701347106998
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 478.36581214602177,
"count": 232235,
"self": 6.466559857010395,
"children": {
"process_trajectory": {
"total": 149.49874962301186,
"count": 232235,
"self": 148.33032135001162,
"children": {
"RLTrainer._checkpoint": {
"total": 1.168428273000245,
"count": 10,
"self": 1.168428273000245
}
}
},
"_update_policy": {
"total": 322.4005026659995,
"count": 97,
"self": 261.7891217080038,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.61138095799572,
"count": 2910,
"self": 60.61138095799572
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4350002857099753e-06,
"count": 1,
"self": 1.4350002857099753e-06
},
"TrainerController._save_models": {
"total": 0.11022693799986882,
"count": 1,
"self": 0.0019872729999406147,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10823966499992821,
"count": 1,
"self": 0.10823966499992821
}
}
}
}
}
}
}